List your company

General Multi-Choice Question Answering on MMLU-Pro

49.4Science AccuracyAutoMR
14.97623.91332.8541.787Oct 5, 2025

Evaluation results

MethodLinks
AutoMRBackbone=Qwen, Skeleton Structure=DAG2025.1049.433.757.445.6
AutoMRBackbone=LLaMA, Skeleton Structure=DAG2025.1048.933.25138.8
MaASBackbone=Qwen, Skeleton Structure=Sequential2025.1045.5315641.7
Meta-ReasonerBackbone=Qwen, Skeleton Structure=Sequential2025.1045.431.95542.2
MaASBackbone=LLaMA, Skeleton Structure=Sequential2025.1044.629.746.235.6
Meta-ReasonerBackbone=LLaMA, Skeleton Structure=Sequential2025.1044.330.647.236.4
rStarBackbone=Qwen, Skeleton Structure=Tree2025.1043.630.855.436
MRPBackbone=Qwen, Skeleton Structure=-2025.1042.830.153.541.6
rStarBackbone=LLaMA, Skeleton Structure=Tree2025.1042.63046.834.8
CoTBackbone=Qwen, Skeleton Structure=Sequential2025.1041.628.351.539.8
MRPBackbone=LLaMA, Skeleton Structure=-2025.1036.424.240.632.8
Direct-I/OBackbone=Qwen, Skeleton Structure=-2025.1032.725.13929.1
CoTBackbone=LLaMA, Skeleton Structure=Sequential2025.1031.522.437.331.3
Direct-I/OBackbone=LLaMA, Skeleton Structure=-2025.1016.311.515.814.5